[Qemu-devel] [5297] Refactor AIO to allow multiple AIO implementations

[Anthony Liguori]

Revision: 5297
          http://svn.sv.gnu.org/viewvc/?view=rev&root=qemu&revision=5297
Author:   aliguori
Date:     2008-09-22 19:17:18 +0000 (Mon, 22 Sep 2008)

Log Message:
-----------
Refactor AIO to allow multiple AIO implementations

This patch refactors the AIO layer to allow multiple AIO implementations.  It's
only possible because of the recent signalfd() patch.  

Right now, the AIO infrastructure is pretty specific to the block raw backend.
For other block devices to implement AIO, the qemu_aio_wait function must
support registration.  This patch introduces a new function,
qemu_aio_set_fd_handler, which can be used to register a file descriptor to be
called back.  qemu_aio_wait() now polls a set of file descriptors registered
with this function until one becomes readable or writable.

This patch should allow the implementation of alternative AIO backends (via a
thread pool or linux-aio) and AIO backends in non-traditional block devices
(like NBD).

Signed-off-by: Anthony Liguori <address@hidden>

Modified Paths:
--------------
    trunk/Makefile
    trunk/Makefile.target
    trunk/block-raw-posix.c
    trunk/block-raw-win32.c
    trunk/block.c
    trunk/block.h

Added Paths:
-----------
    trunk/aio.c
    trunk/qemu-aio.h

Modified: trunk/Makefile
===================================================================
--- trunk/Makefile      2008-09-22 16:52:28 UTC (rev 5296)
+++ trunk/Makefile      2008-09-22 19:17:18 UTC (rev 5297)
@@ -51,7 +51,7 @@
 BLOCK_OBJS+=block-cow.o block-qcow.o aes.o block-vmdk.o block-cloop.o
 BLOCK_OBJS+=block-dmg.o block-bochs.o block-vpc.o block-vvfat.o
 BLOCK_OBJS+=block-qcow2.o block-parallels.o block-nbd.o
-BLOCK_OBJS+=nbd.o block.o
+BLOCK_OBJS+=nbd.o block.o aio.o
 
 ifdef CONFIG_WIN32
 BLOCK_OBJS += block-raw-win32.o

Modified: trunk/Makefile.target
===================================================================
--- trunk/Makefile.target       2008-09-22 16:52:28 UTC (rev 5296)
+++ trunk/Makefile.target       2008-09-22 19:17:18 UTC (rev 5297)
@@ -474,7 +474,7 @@
 ifndef CONFIG_USER_ONLY
 
 OBJS=vl.o osdep.o monitor.o pci.o loader.o isa_mmio.o machine.o net-checksum.o
-OBJS+=fw_cfg.o
+OBJS+=fw_cfg.o aio.o
 ifdef CONFIG_WIN32
 OBJS+=block-raw-win32.o
 else

Added: trunk/aio.c
===================================================================
--- trunk/aio.c                         (rev 0)
+++ trunk/aio.c 2008-09-22 19:17:18 UTC (rev 5297)
@@ -0,0 +1,192 @@
+/*
+ * QEMU aio implementation
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ *  Anthony Liguori   <address@hidden>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "block.h"
+#include "sys-queue.h"
+#include "qemu_socket.h"
+
+typedef struct AioHandler AioHandler;
+
+/* The list of registered AIO handlers */
+static LIST_HEAD(, AioHandler) aio_handlers;
+
+/* This is a simple lock used to protect the aio_handlers list.  Specifically,
+ * it's used to ensure that no callbacks are removed while we're walking and
+ * dispatching callbacks.
+ */
+static int walking_handlers;
+
+struct AioHandler
+{
+    int fd;
+    IOHandler *io_read;
+    IOHandler *io_write;
+    AioFlushHandler *io_flush;
+    int deleted;
+    void *opaque;
+    LIST_ENTRY(AioHandler) node;
+};
+
+static AioHandler *find_aio_handler(int fd)
+{
+    AioHandler *node;
+
+    LIST_FOREACH(node, &aio_handlers, node) {
+        if (node->fd == fd)
+            return node;
+    }
+
+    return NULL;
+}
+
+int qemu_aio_set_fd_handler(int fd,
+                            IOHandler *io_read,
+                            IOHandler *io_write,
+                            AioFlushHandler *io_flush,
+                            void *opaque)
+{
+    AioHandler *node;
+
+    node = find_aio_handler(fd);
+
+    /* Are we deleting the fd handler? */
+    if (!io_read && !io_write) {
+        if (node) {
+            /* If the lock is held, just mark the node as deleted */
+            if (walking_handlers)
+                node->deleted = 1;
+            else {
+                /* Otherwise, delete it for real.  We can't just mark it as
+                 * deleted because deleted nodes are only cleaned up after
+                 * releasing the walking_handlers lock.
+                 */
+                LIST_REMOVE(node, node);
+                qemu_free(node);
+            }
+        }
+    } else {
+        if (node == NULL) {
+            /* Alloc and insert if it's not already there */
+            node = qemu_mallocz(sizeof(AioHandler));
+            if (node == NULL)
+                return -ENOMEM;
+            node->fd = fd;
+            LIST_INSERT_HEAD(&aio_handlers, node, node);
+        }
+        /* Update handler with latest information */
+        node->io_read = io_read;
+        node->io_write = io_write;
+        node->io_flush = io_flush;
+        node->opaque = opaque;
+    }
+
+    qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);
+
+    return 0;
+}
+
+void qemu_aio_flush(void)
+{
+    AioHandler *node;
+    int ret;
+
+    do {
+        ret = 0;
+
+        LIST_FOREACH(node, &aio_handlers, node) {
+            ret |= node->io_flush(node->opaque);
+        }
+
+        qemu_aio_wait();
+    } while (ret > 0);
+}
+
+void qemu_aio_wait(void)
+{
+    int ret;
+
+    if (qemu_bh_poll())
+        return;
+
+    do {
+        AioHandler *node;
+        fd_set rdfds, wrfds;
+        int max_fd = -1;
+
+        walking_handlers = 1;
+
+        /* fill fd sets */
+        LIST_FOREACH(node, &aio_handlers, node) {
+            /* If there aren't pending AIO operations, don't invoke callbacks.
+             * Otherwise, if there are no AIO requests, qemu_aio_wait() would
+             * wait indefinitely.
+             */
+            if (node->io_flush && node->io_flush(node->opaque) == 0)
+                continue;
+
+            if (!node->deleted && node->io_read) {
+                FD_SET(node->fd, &rdfds);
+                max_fd = MAX(max_fd, node->fd + 1);
+            }
+            if (!node->deleted && node->io_write) {
+                FD_SET(node->fd, &wrfds);
+                max_fd = MAX(max_fd, node->fd + 1);
+            }
+        }
+
+        walking_handlers = 0;
+
+        /* No AIO operations?  Get us out of here */
+        if (max_fd == -1)
+            break;
+
+        /* wait until next event */
+        ret = select(max_fd, &rdfds, &wrfds, NULL, NULL);
+        if (ret == -1 && errno == EINTR)
+            continue;
+
+        /* if we have any readable fds, dispatch event */
+        if (ret > 0) {
+            walking_handlers = 1;
+
+            /* we have to walk very carefully in case
+             * qemu_aio_set_fd_handler is called while we're walking */
+            node = LIST_FIRST(&aio_handlers);
+            while (node) {
+                AioHandler *tmp;
+
+                if (!node->deleted &&
+                    FD_ISSET(node->fd, &rdfds) &&
+                    node->io_read) {
+                    node->io_read(node->opaque);
+                }
+                if (!node->deleted &&
+                    FD_ISSET(node->fd, &wrfds) &&
+                    node->io_write) {
+                    node->io_write(node->opaque);
+                }
+
+                tmp = node;
+                node = LIST_NEXT(node, node);
+
+                if (tmp->deleted) {
+                    LIST_REMOVE(tmp, node);
+                    qemu_free(tmp);
+                }
+            }
+
+            walking_handlers = 0;
+        }
+    } while (ret == 0);
+}

Modified: trunk/block-raw-posix.c
===================================================================
--- trunk/block-raw-posix.c     2008-09-22 16:52:28 UTC (rev 5296)
+++ trunk/block-raw-posix.c     2008-09-22 19:17:18 UTC (rev 5297)
@@ -101,6 +101,8 @@
 #endif
 } BDRVRawState;
 
+static int posix_aio_init(void);
+
 static int fd_open(BlockDriverState *bs);
 
 static int raw_open(BlockDriverState *bs, const char *filename, int flags)
@@ -108,6 +110,8 @@
     BDRVRawState *s = bs->opaque;
     int fd, open_flags, ret;
 
+    posix_aio_init();
+
     s->lseek_err_cnt = 0;
 
     open_flags = O_BINARY;
@@ -437,13 +441,15 @@
     int ret;
 } RawAIOCB;
 
-static int aio_sig_fd = -1;
-static int aio_sig_num = SIGUSR2;
-static RawAIOCB *first_aio; /* AIO issued */
-static int aio_initialized = 0;
+typedef struct PosixAioState
+{
+    int fd;
+    RawAIOCB *first_aio;
+} PosixAioState;
 
-static void qemu_aio_poll(void *opaque)
+static void posix_aio_read(void *opaque)
 {
+    PosixAioState *s = opaque;
     RawAIOCB *acb, **pacb;
     int ret;
     size_t offset;
@@ -457,7 +463,7 @@
     while (offset < 128) {
         ssize_t len;
 
-        len = read(aio_sig_fd, sig.buf + offset, 128 - offset);
+        len = read(s->fd, sig.buf + offset, 128 - offset);
         if (len == -1 && errno == EINTR)
             continue;
         if (len == -1 && errno == EAGAIN) {
@@ -472,7 +478,7 @@
     }
 
     for(;;) {
-        pacb = &first_aio;
+        pacb = &s->first_aio;
         for(;;) {
             acb = *pacb;
             if (!acb)
@@ -507,25 +513,37 @@
  the_end: ;
 }
 
-void qemu_aio_init(void)
+static int posix_aio_flush(void *opaque)
 {
-    sigset_t mask;
+    PosixAioState *s = opaque;
+    return !!s->first_aio;
+}
 
-    if (aio_initialized)
-        return;
+static PosixAioState *posix_aio_state;
 
-    aio_initialized = 1;
+static int posix_aio_init(void)
+{
+    sigset_t mask;
+    PosixAioState *s;
+  
+    if (posix_aio_state)
+        return 0;
 
+    s = qemu_malloc(sizeof(PosixAioState));
+    if (s == NULL)
+        return -ENOMEM;
+
     /* Make sure to block AIO signal */
     sigemptyset(&mask);
-    sigaddset(&mask, aio_sig_num);
+    sigaddset(&mask, SIGUSR2);
     sigprocmask(SIG_BLOCK, &mask, NULL);
     
-    aio_sig_fd = qemu_signalfd(&mask);
+    s->first_aio = NULL;
+    s->fd = qemu_signalfd(&mask);
 
-    fcntl(aio_sig_fd, F_SETFL, O_NONBLOCK);
+    fcntl(s->fd, F_SETFL, O_NONBLOCK);
 
-    qemu_set_fd_handler2(aio_sig_fd, NULL, qemu_aio_poll, NULL, NULL);
+    qemu_aio_set_fd_handler(s->fd, posix_aio_read, NULL, posix_aio_flush, s);
 
 #if defined(__GLIBC__) && defined(__linux__)
     {
@@ -539,41 +557,11 @@
         aio_init(&ai);
     }
 #endif
-}
+    posix_aio_state = s;
 
-/* Wait for all IO requests to complete.  */
-void qemu_aio_flush(void)
-{
-    qemu_aio_poll(NULL);
-    while (first_aio) {
-        qemu_aio_wait();
-    }
+    return 0;
 }
 
-void qemu_aio_wait(void)
-{
-    int ret;
-
-    if (qemu_bh_poll())
-        return;
-
-    if (!first_aio)
-        return;
-
-    do {
-        fd_set rdfds;
-
-        FD_ZERO(&rdfds);
-        FD_SET(aio_sig_fd, &rdfds);
-
-        ret = select(aio_sig_fd + 1, &rdfds, NULL, NULL, NULL);
-        if (ret == -1 && errno == EINTR)
-            continue;
-    } while (ret == 0);
-
-    qemu_aio_poll(NULL);
-}
-
 static RawAIOCB *raw_aio_setup(BlockDriverState *bs,
         int64_t sector_num, uint8_t *buf, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque)
@@ -588,7 +576,7 @@
     if (!acb)
         return NULL;
     acb->aiocb.aio_fildes = s->fd;
-    acb->aiocb.aio_sigevent.sigev_signo = aio_sig_num;
+    acb->aiocb.aio_sigevent.sigev_signo = SIGUSR2;
     acb->aiocb.aio_sigevent.sigev_notify = SIGEV_SIGNAL;
     acb->aiocb.aio_buf = buf;
     if (nb_sectors < 0)
@@ -596,8 +584,8 @@
     else
         acb->aiocb.aio_nbytes = nb_sectors * 512;
     acb->aiocb.aio_offset = sector_num * 512;
-    acb->next = first_aio;
-    first_aio = acb;
+    acb->next = posix_aio_state->first_aio;
+    posix_aio_state->first_aio = acb;
     return acb;
 }
 
@@ -688,7 +676,7 @@
     }
 
     /* remove the callback from the queue */
-    pacb = &first_aio;
+    pacb = &posix_aio_state->first_aio;
     for(;;) {
         if (*pacb == NULL) {
             break;
@@ -701,21 +689,10 @@
     }
 }
 
-# else /* CONFIG_AIO */
-
-void qemu_aio_init(void)
+#else /* CONFIG_AIO */
+static int posix_aio_init(void)
 {
 }
-
-void qemu_aio_flush(void)
-{
-}
-
-void qemu_aio_wait(void)
-{
-    qemu_bh_poll();
-}
-
 #endif /* CONFIG_AIO */
 
 static void raw_close(BlockDriverState *bs)
@@ -921,6 +898,8 @@
     BDRVRawState *s = bs->opaque;
     int fd, open_flags, ret;
 
+    posix_aio_init();
+
 #ifdef CONFIG_COCOA
     if (strstart(filename, "/dev/cdrom", NULL)) {
         kern_return_t kernResult;

Modified: trunk/block-raw-win32.c
===================================================================
--- trunk/block-raw-win32.c     2008-09-22 16:52:28 UTC (rev 5296)
+++ trunk/block-raw-win32.c     2008-09-22 19:17:18 UTC (rev 5297)
@@ -339,19 +339,6 @@
     return 0;
 }
 
-void qemu_aio_init(void)
-{
-}
-
-void qemu_aio_flush(void)
-{
-}
-
-void qemu_aio_wait(void)
-{
-    qemu_bh_poll();
-}
-
 BlockDriver bdrv_raw = {
     "raw",
     sizeof(BDRVRawState),

Modified: trunk/block.c
===================================================================
--- trunk/block.c       2008-09-22 16:52:28 UTC (rev 5296)
+++ trunk/block.c       2008-09-22 19:17:18 UTC (rev 5297)
@@ -1310,8 +1310,6 @@
     bdrv_register(&bdrv_qcow2);
     bdrv_register(&bdrv_parallels);
     bdrv_register(&bdrv_nbd);
-
-    qemu_aio_init();
 }
 
 void *qemu_aio_get(BlockDriverState *bs, BlockDriverCompletionFunc *cb,

Modified: trunk/block.h
===================================================================
--- trunk/block.h       2008-09-22 16:52:28 UTC (rev 5296)
+++ trunk/block.h       2008-09-22 19:17:18 UTC (rev 5297)
@@ -1,6 +1,8 @@
 #ifndef BLOCK_H
 #define BLOCK_H
 
+#include "qemu-aio.h"
+
 /* block.c */
 typedef struct BlockDriver BlockDriver;
 
@@ -87,10 +89,6 @@
                                  BlockDriverCompletionFunc *cb, void *opaque);
 void bdrv_aio_cancel(BlockDriverAIOCB *acb);
 
-void qemu_aio_init(void);
-void qemu_aio_flush(void);
-void qemu_aio_wait(void);
-
 int qemu_key_check(BlockDriverState *bs, const char *name);
 
 /* Ensure contents are flushed to disk.  */

Added: trunk/qemu-aio.h
===================================================================
--- trunk/qemu-aio.h                            (rev 0)
+++ trunk/qemu-aio.h    2008-09-22 19:17:18 UTC (rev 5297)
@@ -0,0 +1,45 @@
+/*
+ * QEMU aio implementation
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ *  Anthony Liguori   <address@hidden>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_AIO_H
+#define QEMU_AIO_H
+
+#include "qemu-common.h"
+#include "qemu-char.h"
+
+/* Returns 1 if there are still outstanding AIO requests; 0 otherwise */
+typedef int (AioFlushHandler)(void *opaque);
+
+/* Flush any pending AIO operation. This function will block until all
+ * outstanding AIO operations have been completed or cancelled. */
+void qemu_aio_flush(void);
+
+/* Wait for a single AIO completion to occur.  This function will until a
+ * single AIO opeartion has completed.  It is intended to be used as a looping
+ * primative when simulating synchronous IO based on asynchronous IO. */
+void qemu_aio_wait(void);
+
+/* Register a file descriptor and associated callbacks.  Behaves very similarly
+ * to qemu_set_fd_handler2.  Unlike qemu_set_fd_handler2, these callbacks will
+ * be invoked when using either qemu_aio_wait() or qemu_aio_flush().
+ *
+ * Code that invokes AIO completion functions should rely on this function
+ * instead of qemu_set_fd_handler[2].
+ */
+int qemu_aio_set_fd_handler(int fd,
+                            IOHandler *io_read,
+                            IOHandler *io_write,
+                            AioFlushHandler *io_flush,
+                            void *opaque);
+
+#endif